Soumyajit Chatterjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Soumyajit Chatterjee has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Sandip Chakraborty
IIT Kharagpur, Kharagpur, West Bengal, India
7 shared publications - Subrata Nandi
National Institute of Technology
3 shared publications - Bivas Mitra
IIT Kharagpur
2 shared publications - Fahim Kawsar
University of Glasgow
2 shared publications - Mohammad Malekzadeh
Nokia Bell Labs, Cambridge, United Kingdom
2 shared publications - Mousumi Saha
National Institute of Technology Durgapur
2 shared publications
Latest Publications
- Open Access
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 465-477
BoTTA: Benchmarking On-device Test Time Adaptation
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 465-477
Open AccessBoTTA: Benchmarking On-device Test Time Adaptation
- Open Access
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 636-645
Short Paper: Towards Real-Time ECG and EMG Modeling on μNPUs
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 636-645
Open AccessShort Paper: Towards Real-Time ECG and EMG Modeling on μNPUs
- Open Access
- 3 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Enhancing Efficiency in Multidevice Federated Learning through Data Selection
- 3 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open AccessEnhancing Efficiency in Multidevice Federated Learning through Data Selection
- Open Access
- 24 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (6) , 1-25
Evaluating Large Language Models as Virtual Annotators for Time-Series Physical Sensing Data
Traditional human-in-the-loop-based annotation for time-series data like inertial data often requires access to alternate modalities like video or audio from the environment. These alternate sources provide the necessary information to the human annotator, as the raw numeric data are often too obfuscated even for an expert. However, this traditional approach has many concerns surrounding overall cost, efficiency, storage of additional modalities, time, scalability, and privacy. Interestingly, recent large language models (LLMs) are also trained with vast amounts of publicly available alphanumeric data, which allows them to comprehend and perform well on tasks beyond natural language processing. Naturally, this opens up a potential avenue to explore the opportunities in using these LLMs as virtual annotators where the LLMs will be directly provided the raw sensor data for annotation instead of relying on any alternate modality. Naturally, this could mitigate the problems of the traditional human-in-the-loop approach. Motivated by this observation, we perform a detailed study in this article to assess whether the state-of-the-art (SOTA) LLMs can be used as virtual annotators for labeling time-series physical sensing data. To perform this in a principled manner, we segregate the study into two major phases. In the first phase, we investigate the challenges an LLM like GPT-4 faces in comprehending raw sensor data. Considering the observations from Phase 1, in the next phase, we investigate the possibility of encoding the raw sensor data using SOTA SSL approaches and utilizing the projected time-series data to get annotations from the LLM. Detailed evaluation with four benchmark HAR datasets shows that SSL-based encoding and metric-based guidance allow the LLM to make more reasonable decisions and provide accurate annotations without requiring computationally expensive fine-tuning or sophisticated prompt engineering.
- 24 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (6) , 1-25
Open AccessEvaluating Large Language Models as Virtual Annotators for Time-Series Physical Sensing Data
Traditional human-in-the-loop-based annotation for time-series data like inertial data often requires access to alternate modalities like video or audio from the environment. These alternate sources provide the necessary information to the human annotator, as the raw numeric data are often too obfuscated even for an expert. However, this traditional approach has many concerns surrounding overall cost, efficiency, storage of additional modalities, time, scalability, and privacy. Interestingly, recent large language models (LLMs) are also trained with vast amounts of publicly available alphanumeric data, which allows them to comprehend and perform well on tasks beyond natural language processing. Naturally, this opens up a potential avenue to explore the opportunities in using these LLMs as virtual annotators where the LLMs will be directly provided the raw sensor data for annotation instead of relying on any alternate modality. Naturally, this could mitigate the problems of the traditional human-in-the-loop approach. Motivated by this observation, we perform a detailed study in this article to assess whether the state-of-the-art (SOTA) LLMs can be used as virtual annotators for labeling time-series physical sensing data. To perform this in a principled manner, we segregate the study into two major phases. In the first phase, we investigate the challenges an LLM like GPT-4 faces in comprehending raw sensor data. Considering the observations from Phase 1, in the next phase, we investigate the possibility of encoding the raw sensor data using SOTA SSL approaches and utilizing the projected time-series data to get annotations from the LLM. Detailed evaluation with four benchmark HAR datasets shows that SSL-based encoding and metric-based guidance allow the LLM to make more reasonable decisions and provide accurate annotations without requiring computationally expensive fine-tuning or sophisticated prompt engineering.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1565-1568
WellComp 2025: Eighth International Workshop on Computing and Software Systems for Well-Being
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1565-1568
Open AccessWellComp 2025: Eighth International Workshop on Computing and Software Systems for Well-Being
- Open Access
- 28 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 139
Poster: Test-time Training for Sensor Data Classification via Time-series Change Identification
Test-time heterogeneity is the root cause of domain shift, which hinders IMU-based human activity recognition (HAR). We devise a test-time training approach that utilizes the temporal properties of time series to assess the shift induced by changes in body position and use them to calibrate the model at test time. Experimental results show that accuracy improves after calibrating the model.
- 28 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 139
Open AccessPoster: Test-time Training for Sensor Data Classification via Time-series Change Identification
Test-time heterogeneity is the root cause of domain shift, which hinders IMU-based human activity recognition (HAR). We devise a test-time training approach that utilizes the temporal properties of time series to assess the shift induced by changes in body position and use them to calibrate the model at test time. Experimental results show that accuracy improves after calibrating the model.
- Open Access
"Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living
Complex activities of daily living (ADLs) often consist of multiple micro-activities. When performed sequentially, these micro-activities help the user accomplish the broad macro-activity. Naturally, a deeper understanding of these micro-activities can help develop more sophisticated human activity recognition (HAR) models and add explainability to their inferred conclusions. Previous research has attempted to achieve this by utilizing fine-grained annotated data that provided the required supervision and rules for associating the micro-activities to identify the macro-activity. However, this ``bottom-up'' approach is unrealistic as getting such high-quality, fine-grained annotated sensor datasets is challenging, costly, and time-consuming. Understanding this, in this paper, we develop AmicroN, which adapts a ``top-down'' approach by exploiting coarse-grained annotated data to expand the macro-activities into their constituent micro-activities without any external supervision. In the backend, AmicroN uses \textit{unsupervised} change-point detection to search for the micro-activity boundaries across a complex ADL. Then, it applies a \textit{generalized zero-shot} approach to characterize it. We evaluate AmicroN on two real-life publicly available datasets and observe that AmicroN can identify the micro-activities with micro F\textsubscript{1}-score $>0.75$ for both datasets. Additionally, we also perform an initial proof-of-concept on leveraging the state-of-the-art (SOTA) large language models (LLMs) with attribute embeddings predicted by AmicroN to enhance further the explainability surrounding the detection of micro-activities.Open Access"Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living
Complex activities of daily living (ADLs) often consist of multiple micro-activities. When performed sequentially, these micro-activities help the user accomplish the broad macro-activity. Naturally, a deeper understanding of these micro-activities can help develop more sophisticated human activity recognition (HAR) models and add explainability to their inferred conclusions. Previous research has attempted to achieve this by utilizing fine-grained annotated data that provided the required supervision and rules for associating the micro-activities to identify the macro-activity. However, this ``bottom-up'' approach is unrealistic as getting such high-quality, fine-grained annotated sensor datasets is challenging, costly, and time-consuming. Understanding this, in this paper, we develop AmicroN, which adapts a ``top-down'' approach by exploiting coarse-grained annotated data to expand the macro-activities into their constituent micro-activities without any external supervision. In the backend, AmicroN uses \textit{unsupervised} change-point detection to search for the micro-activity boundaries across a complex ADL. Then, it applies a \textit{generalized zero-shot} approach to characterize it. We evaluate AmicroN on two real-life publicly available datasets and observe that AmicroN can identify the micro-activities with micro F\textsubscript{1}-score $>0.75$ for both datasets. Additionally, we also perform an initial proof-of-concept on leveraging the state-of-the-art (SOTA) large language models (LLMs) with attribute embeddings predicted by AmicroN to enhance further the explainability surrounding the detection of micro-activities. - Open Access
- 1 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 19 (3) , 1-30
AQuaMoHo : Localized Low-cost Outdoor Air Quality Sensing over a Thermo-hygrometer
Efficient air quality sensing serves as one of the essential services provided in any recent smart city. Mostly facilitated by sparsely deployed Air Quality Monitoring Stations (AQMSs) that are difficult to install and maintain, the overall spatial variation heavily impacts air quality monitoring for locations far enough from these pre-deployed public infrastructures. To mitigate this, we in this article propose a framework named AQuaMoHo that can annotate data obtained from a low-cost thermo-hygrometer (as the sole physical sensing device) with the AQI labels, with the help of additional publicly crawled Spatio-temporal information of that locality. At its core, AQuaMoHo exploits the temporal patterns from a set of readily available spatial features using an LSTM-based model and further enhances the overall quality of the annotation using temporal attention. From a thorough study of two different cities, we observe that AQuaMoHo can significantly help annotate the air quality data on a personal scale.
- 1 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 19 (3) , 1-30
Open AccessAQuaMoHo : Localized Low-cost Outdoor Air Quality Sensing over a Thermo-hygrometer
Efficient air quality sensing serves as one of the essential services provided in any recent smart city. Mostly facilitated by sparsely deployed Air Quality Monitoring Stations (AQMSs) that are difficult to install and maintain, the overall spatial variation heavily impacts air quality monitoring for locations far enough from these pre-deployed public infrastructures. To mitigate this, we in this article propose a framework named AQuaMoHo that can annotate data obtained from a low-cost thermo-hygrometer (as the sole physical sensing device) with the AQI labels, with the help of additional publicly crawled Spatio-temporal information of that locality. At its core, AQuaMoHo exploits the temporal patterns from a set of readily available spatial features using an LSTM-based model and further enhances the overall quality of the annotation using temporal attention. From a thorough study of two different cities, we observe that AQuaMoHo can significantly help annotate the air quality data on a personal scale.
- Open Access
- 23 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Internet of Things
- Vol. 4 (1) , 1-24
Exploiting Multi-modal Contextual Sensing for City-bus’s Stay Location Characterization: Towards Sub-60 Seconds Accurate Arrival Time Prediction
Intelligent city transportation systems are one of the core infrastructures of a smart city. The true ingenuity of such an infrastructure lies in providing the commuters with real-time information about citywide transport like public buses, allowing them to pre-plan their travel. However, providing prior information for transportation systems like public buses in real-time is inherently challenging because of the diverse nature of different stay-locations where a public bus stops. Although straightforward factors like stay duration extracted from unimodal sources like GPS at these locations look erratic, a thorough analysis of public bus GPS trails for 1,335.365 km at the city of Durgapur, a semi-urban city in India, reveals that several other fine-grained contextual features can characterize these locations accurately. Accordingly, we develop BuStop , a system for extracting and characterizing the stay-locations from multi-modal sensing using commuters’ smartphones. Using this multi-modal information BuStop extracts a set of granular contextual features that allows the system to differentiate among the different stay-location types. A thorough analysis of BuStop using the collected in-house dataset indicates that the system works with high accuracy in identifying different stay-locations such as regular bus stops, random ad hoc stops, stops due to traffic congestion, stops at traffic signals, and stops at sharp turns. Additionally, we develop a proof-of-concept setup on top of BuStop to analyze the potential of the framework in predicting expected arrival time, a critical piece of information required to pre-plan travel at any given bus stop. Subsequent analysis of the PoC framework, through simulation over the test dataset, shows that characterizing the stay-locations indeed helps make more accurate arrival time predictions with deviations less than 60 seconds from the ground-truth arrival time.
- 23 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Internet of Things
- Vol. 4 (1) , 1-24
Open AccessExploiting Multi-modal Contextual Sensing for City-bus’s Stay Location Characterization: Towards Sub-60 Seconds Accurate Arrival Time Prediction
Intelligent city transportation systems are one of the core infrastructures of a smart city. The true ingenuity of such an infrastructure lies in providing the commuters with real-time information about citywide transport like public buses, allowing them to pre-plan their travel. However, providing prior information for transportation systems like public buses in real-time is inherently challenging because of the diverse nature of different stay-locations where a public bus stops. Although straightforward factors like stay duration extracted from unimodal sources like GPS at these locations look erratic, a thorough analysis of public bus GPS trails for 1,335.365 km at the city of Durgapur, a semi-urban city in India, reveals that several other fine-grained contextual features can characterize these locations accurately. Accordingly, we develop BuStop , a system for extracting and characterizing the stay-locations from multi-modal sensing using commuters’ smartphones. Using this multi-modal information BuStop extracts a set of granular contextual features that allows the system to differentiate among the different stay-location types. A thorough analysis of BuStop using the collected in-house dataset indicates that the system works with high accuracy in identifying different stay-locations such as regular bus stops, random ad hoc stops, stops due to traffic congestion, stops at traffic signals, and stops at sharp turns. Additionally, we develop a proof-of-concept setup on top of BuStop to analyze the potential of the framework in predicting expected arrival time, a critical piece of information required to pre-plan travel at any given bus stop. Subsequent analysis of the PoC framework, through simulation over the test dataset, shows that characterizing the stay-locations indeed helps make more accurate arrival time predictions with deviations less than 60 seconds from the ground-truth arrival time.
- Open Access
AQuaMoHo: Localized Low-Cost Outdoor Air Quality Sensing over a Thermo-Hygrometer
Efficient air quality sensing serves as one of the essential services provided in any recent smart city. Mostly facilitated by sparsely deployed Air Quality Monitoring Stations (AQMSs) that are difficult to install and maintain, the overall spatial variation heavily impacts air quality monitoring for locations far enough from these pre-deployed public infrastructures. To mitigate this, we in this paper propose a framework named AQuaMoHo that can annotate data obtained from a low-cost thermo-hygrometer (as the sole physical sensing device) with the AQI labels, with the help of additional publicly crawled Spatio-temporal information of that locality. At its core, AQuaMoHo exploits the temporal patterns from a set of readily available spatial features using an LSTM-based model and further enhances the overall quality of the annotation using temporal attention. From a thorough study of two different cities, we observe that AQuaMoHo can significantly help annotate the air quality data on a personal scale.
Open AccessAQuaMoHo: Localized Low-Cost Outdoor Air Quality Sensing over a Thermo-Hygrometer
Efficient air quality sensing serves as one of the essential services provided in any recent smart city. Mostly facilitated by sparsely deployed Air Quality Monitoring Stations (AQMSs) that are difficult to install and maintain, the overall spatial variation heavily impacts air quality monitoring for locations far enough from these pre-deployed public infrastructures. To mitigate this, we in this paper propose a framework named AQuaMoHo that can annotate data obtained from a low-cost thermo-hygrometer (as the sole physical sensing device) with the AQI labels, with the help of additional publicly crawled Spatio-temporal information of that locality. At its core, AQuaMoHo exploits the temporal patterns from a set of readily available spatial features using an LSTM-based model and further enhances the overall quality of the annotation using temporal attention. From a thorough study of two different cities, we observe that AQuaMoHo can significantly help annotate the air quality data on a personal scale.